© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 57673
    Prev
    Next
    INDEX
    Explanations

    make concepts easy or create something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uent
    -0.09
    OTO
    -0.09
     altern
    -0.09
     deserted
    -0.08
     Joker
    -0.08
    Altern
    -0.08
    uko
    -0.08
    Æ°
    -0.08
    alte
    -0.08
    olf
    -0.08
    POSITIVE LOGITS
     ordinary
    0.10
     transforms
    0.09
    arel
    0.09
     transforming
    0.09
    anh
    0.09
     Wald
    0.09
     mundane
    0.09
     Rae
    0.08
    eler
    0.08
     Ø®
    0.08
    Activations Density 0.072%

    No Known Activations